Comments (1)
Hi fapeci,
Currently, users are expected to evaluate models locally on their own machines. At some point, the video frame data needs be loaded into your machine's memory for evaluation, and you are free to do that in anyway you would like.
If you are simply interested in evaluating videos you find on the web, there exists many command line utilities such as wget
and youtube-dl
that make it very easy to download videos from the web. For example, if I wanted to predict the action in this juggling video I found on the Moments Explore Page, I could download and evaluate it using:
wget http://data.csail.mit.edu/soundnet/actions3/juggling/vine-hWJwDv3eK9B_1.mp4
python test_video.py --video_file vine-hWJwDv3eK9B_1.mp4
Of course, you could write more sophisticated scripts that automate some of this, but I'll leave that up to you :). Hope that helps!
Alex
from moments_models.
Related Issues (20)
- test_model.py update HOT 1
- Not an issue, but a question
- test_video.py - AttributeError: 'NoneType' object has no attribute 'groups' HOT 2
- Data prep scripts for the Moments in Time dataset
- Can you post some accuracy results of the pretrained models? HOT 1
- Help:Reg Action Recognition Dataset
- Fine-tuning the TRN model (InceptionV3 backbone) trained on the Moments for something-something-v2 dataset HOT 2
- Frames are not sorted properly in test_video.py
- Frames are not sorted properly in test_video.py
- No such file or directory:'moments_RGB_resnet50_imagenetpretrained.pth.tar' HOT 3
- resnet3d50 model architecture HOT 1
- where is warp_r in loss_functions.py #44 HOT 1
- Which activation function to apply before wLSEP loss? HOT 1
- The mAP for res3d50 model is much lower than 0.6 HOT 1
- How to use this pretrained resnet50 model in android, is there any specific conversion steps?
- How do you compute Top-1/5 accuracies for Multi-Moments (multi-label)?
- Number of classes HOT 1
- Error running test_model.py HOT 1
- Difference in result on TRN-pytorch example HOT 2
- Suggestion for Readme.md
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from moments_models.